Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Punctuation and "of" and "the"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icus
    -0.07
    托
    -0.07
    施
    -0.07
    enia
    -0.07
    uster
    -0.06
    Dom
    -0.06
     GetName
    -0.06
    แม
    -0.06
     콜
    -0.06
    =self
    -0.06
    POSITIVE LOGITS
    .swift
    0.06
     fot
    0.06
    .FileSystem
    0.06
     impressive
    0.06
    Folders
    0.06
     gradients
    0.06
    FUNCTION
    0.06
    .toLowerCase
    0.06
    .clip
    0.06
    .random
    0.05
    Act Density 0.013%

    No Known Activations